Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6647
    Prev
    Next
    INDEX
    Explanations

    text fragments containing special characters and keywords like "infowars," "gur," and "Facebook."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant organizations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.78
     compan
    -0.75
     stride
    -0.72
     opp
    -0.68
     Cyborg
    -0.66
     favoured
    -0.64
     chosen
    -0.63
     existing
    -0.62
     awa
    -0.62
     depending
    -0.61
    POSITIVE LOGITS
    Associated
    0.94
    News
    0.85
    SPONSORED
    0.83
    encer
    0.82
    edia
    0.79
    Topics
    0.77
    Morning
    0.77
    videos
    0.77
    eport
    0.77
    tnc
    0.76
    Activations Density 0.186%

    No Known Activations